https://github.com/erikbjare/thesis
MSc thesis on: Classifying brain activity using EEG and automated time tracking of computer use (using ActivityWatch)
https://github.com/erikbjare/thesis
activitywatch eeg machine-learning msc-thesis muse neurosity openbci research thesis
Last synced: 4 months ago
JSON representation
MSc thesis on: Classifying brain activity using EEG and automated time tracking of computer use (using ActivityWatch)
- Host: GitHub
- URL: https://github.com/erikbjare/thesis
- Owner: ErikBjare
- Created: 2020-05-08T10:33:51.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2023-11-13T10:29:12.000Z (over 1 year ago)
- Last Synced: 2025-01-11T15:44:18.564Z (4 months ago)
- Topics: activitywatch, eeg, machine-learning, msc-thesis, muse, neurosity, openbci, research, thesis
- Language: Python
- Homepage: https://erik.bjareholt.com/thesis/
- Size: 130 MB
- Stars: 74
- Watchers: 6
- Forks: 4
- Open Issues: 16
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
MSc Thesis
==========
[](https://github.com/ErikBjare/thesis/actions)
[](https://codecov.io/gh/ErikBjare/thesis)
[](http://mypy-lang.org/)
[](https://github.com/psf/black)
My MSc thesis on "Classifying brain activity using electroencephalography and automated time tracking of computer use".
Progress was tracked using GitHub issues and the [GitHub Projects board](https://github.com/ErikBjare/thesis/projects/1).
# Abstract
> We investigate the ability of EEG to distinguish between different activities users engage in on their devices, building on previous research which showed a considerable difference in brain activity between code- and prose-comprehension, as well as differences during code- and prose-synthesis. We perform a replication study and improve upon past results using state-of-the-art machine learning classifiers based on Riemannian geometry.
>
> Furthermore, we extend the scope of previous work by introducing the automated time tracking application ActivityWatch, to track the device activities that the user is engaging in. This lets us label EEG data with naturalistic device activity, which we then use to train classifiers to discern activities such as code writing vs prose writing, or work vs media consumption. Our results indicate that a consumer-grade EEG device can discern between different activities that a user performs at the computer. Among other results, we show that not only can code and prose *comprehension* be distinguished, but also code and prose *writing*.
# Writing
The latest version of the writing can be downloaded at:
- Thesis report: [erik.bjareholt.com/thesis/thesis.pdf][thesis]
- Goal document: [erik.bjareholt.com/thesis/goaldoc.pdf][goaldoc]
- Presentation: [erik.bjareholt.com/thesis/presentation.pdf][presentation]
- Popular scientific article (Swedish): [erik.bjareholt.com/thesis/popsci.pdf][popsci]
# Usage
Setting it up:
- Ensure you have Python 3.7+ and `poetry` installed
- Install dependencies with `poetry install`
Collecting data:
- Run `eegwatch --help` for instructions on how to collect EEG data
- Run [ActivityWatch](https://activitywatch.net) to collect device activity data
- Run the codeprose task in [eeg-notebooks][eegnb] to collect data for the code vs prose task
- Install eeg-notebooks with `pip install git+`
- Run the codeprose task with `eegnb runexp -ex visual-codeprose -subject X`
Running classifier:
- Run `./scripts/query_aw.py` to collect labels from the running ActivityWatch instance
- You probably want to adjust the categorization rules embedded in the file
- (TODO) Run `eegclassify --help` for instructions on how to train and run the classifier
# Devices
I've worked with multiple devices, but the experiments were performed using the Muse S, which is therefore the best-supported device.
- Muse S
- PPG support (experimental)
- Neurosity Notion 1 & 2
- Thanks to [@andrewjaykeller](https://github.com/andrewjaykeller) at [@neurosity](https://github.com/neurosity) for sending me a refurbished Notion 1 to test with!
- Neurosity Crown
- OpenBCI Cyton
- In theory: any device supported by Brainflow or muse-lsl
# Notebooks
Code notebooks are built in CI and available at:
- [Main][nbmain] - primary notebook for the thesis, where we train a classifier for the code vs prose comprehension task.
- [Signal][nbsignal] - for signal filtering and quality checking.
- [Activity][nbactivity] - for classification of device activities.
- [PPG][nbppg] - for a basic PPG analysis.
[nbmain]: https://erik.bjareholt.com/thesis/Main.html
[nbsignal]: https://erik.bjareholt.com/thesis/Signal.html
[nbactivity]: https://erik.bjareholt.com/thesis/Activity.html
[nbppg]: https://erik.bjareholt.com/thesis/PPG.html
# Acknowledgements
See the Acknowledgements section in the [thesis][thesis].
[thesis]: https://erik.bjareholt.com/thesis/thesis.pdf
[goaldoc]: https://erik.bjareholt.com/thesis/goaldocument.pdf
[presentation]: https://erik.bjareholt.com/thesis/presentation.pdf
[popsci]: https://erik.bjareholt.com/thesis/popsci.pdf
[eegnb]: https://github.com/NeuroTechX/eeg-notebooks